Title :
Multi-PN-learning for tracking applications
Author :
van de Ven, Jasper ; Kreutzmann, Arne ; Schrader, Sascha ; Dylla, Frank
Author_Institution :
Cognitive Syst. Group, Univ. of Bremen, Bremen, Germany
Abstract :
We present a general multi-target tracker able to simultaneously track, learn, and distinguish arbitrary objects in a single video stream and recognize them again after a temporal disappearance (reentering). We show how this tracker can be created as an extension of a general single-target tracker. Furthermore, we provide evidence that dissimilarities of tracked objects and relations in the learned knowledge can be exploited to improve individual tracking results.
Keywords :
computer vision; learning (artificial intelligence); object tracking; Multi-PN learning; computer vision; general single target tracker; knowledge learning; multitarget tracker; temporal disappearance; tracking applications; video stream; Accuracy; Benchmark testing; Detectors; Interpolation; Streaming media; Target tracking;
Conference_Titel :
Control Automation Robotics & Vision (ICARCV), 2014 13th International Conference on
DOI :
10.1109/ICARCV.2014.7064407
